Triple
T19731188
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Queen Sudeshna |
E473856
|
entity |
| Predicate | kingdom |
P567
|
FINISHED |
| Object | Matsya |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Matsya | Statement: [Queen Sudeshna, kingdom, Matsya]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matsya Context triple: [Queen Sudeshna, kingdom, Matsya]
-
A.
Matsya
Matsya was an ancient Indo-Aryan kingdom of northwestern India, often associated with the region around modern Rajasthan and mentioned in early Vedic and epic literature.
-
B.
Matsya
chosen
Matsya is the fish incarnation of the Hindu god Vishnu, known for saving the sacred scriptures and the first man from a great deluge.
-
C.
Garsaura
Garsaura was an ancient settlement in central Anatolia, known as the historical predecessor of the modern Turkish city of Aksaray.
-
D.
Ikan
Ikan is an alternative name for the Ukaan language, a lesser-known Niger-Congo language spoken in parts of Nigeria.
-
E.
Sturgeon
Sturgeon is a surname most prominently associated with Nicola Sturgeon, the former First Minister of Scotland and leader of the Scottish National Party.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8e517ebd48190979ee76723bcfadf |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e649fd18148190a6e85b2be0069dde |
completed | April 20, 2026, 3:45 p.m. |
Created at: April 10, 2026, 1:47 p.m.